© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89471
    Prev
    Next
    INDEX
    Explanations

    buoy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ureka
    -0.28
    ctor
    -0.27
     textColor
    -0.26
     Til
    -0.25
    correct
    -0.24
     til
    -0.24
     queryInterface
    -0.24
    rello
    -0.23
     volte
    -0.23
     correct
    -0.23
    POSITIVE LOGITS
    ä¸Ģ大åłĨ
    0.27
    çīµå¤´
    0.25
    TY
    0.25
     cohort
    0.25
    åį°è±¡æ·±åĪ»
    0.25
    å¤Ķ
    0.25
    ety
    0.25
    åѤç«ĭ
    0.24
     bidi
    0.24
     differentiation
    0.24
    Activations Density 6.505%

    No Known Activations